Blog

Research, model releases, and engineering notes from The Token Company.

Compressing Conversational Context Without Losing the Thread
Research

Compressing Conversational Context Without Losing the Thread

Bear-2 compression improved CoQA accuracy from 93.3% to 95.3% while cutting tokens by 8.2%. Why meeting transcripts and multi-turn conversations compress better than you'd expect.

June 2026

Introducing Bear-2-Safety
Research

Introducing Bear-2-Safety

Token-deletion compression for safety classification pipelines. Cut classifier costs by 30% while preserving or improving F1 across Llama-Guard, ShieldGemma, and Gemini.

June 2026

One of the biggest token consumers globally improved quality by removing context bloat
Case Study

One of the biggest token consumers globally improved quality by removing context bloat

Processing 193B tokens/month, Pax Historia ran a 268K-vote model arena. Compressed models scored higher and A/B tests showed +5% purchase lift.

February 2026

Helonic: cutting inference costs while maintaining quality
Case Study

Helonic: cutting inference costs while maintaining quality

How Helonic uses token compression to reduce LLM API costs without sacrificing output quality.

February 2026